Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    youtube channel links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    łą
    0.42
     atrop
    0.42
    }}_
    0.41
     estrogens
    0.40
     coasters
    0.40
    ۍ
    0.38
    CCl
    0.38
     হাত
    0.37
    嫦
    0.37
    COc
    0.37
    POSITIVE LOGITS
    Mr
    0.49
     Mr
    0.48
     User
    0.41
     USER
    0.41
     Lectures
    0.41
     Channels
    0.40
     user
    0.39
    user
    0.38
     Friendship
    0.37
    віт
    0.37
    Act Density 0.000%

    No Known Activations